In the field of sequential recommendation, deep learning (DL)-based methods have received a lot of attention in the past few years and surpassed traditional models such as Markov chain-based and factorization-based ones. However, there is little systematic study on DL-based methods, especially regarding to how to design an effective DL model for sequential recommendation. In this view, this survey focuses on DL-based sequential recommender systems by taking the aforementioned issues into consideration. Specifically,we illustrate the concept of sequential recommendation, propose a categorization of existing algorithms in terms of three types of behavioral sequence, summarize the key factors affecting the performance of DL-based models, and conduct corresponding evaluations to demonstrate the effects of these factors. We conclude this survey by systematically outlining future directions and challenges in this field.

Deep Learning for Sequential Recommendation: Algorithms, Influential Factors, and Evaluations

In the field of sequential recommendation, deep learning--(DL) based methods have received a lot of attention in the past few years and surpassed traditional models such as Markov chain-based and factorization-based ones. However, there is little systematic study on DL-based methods, especially regarding how to design an effective DL model for sequential recommendation. In this view, this survey focuses on DL-based sequential recommender systems by taking the aforementioned issues into consideration. Specifically, we illustrate the concept of sequential recommendation, propose a categorization of existing algorithms in terms of three types of behavioral sequences, summarize the key factors affecting the performance of DL-based models, and conduct corresponding evaluations to showcase and demonstrate the effects of these factors. We conclude this survey by systematically outlining future directions and challenges in this field.

Recommendation system is able to shape user demands, which can be used for boosting caching gain. In this paper, we jointly optimize content caching and recommendation at base stations to maximize the caching gain meanwhile not compromising the user preference. We first propose a model to capture the impact of recommendation on user demands, which is controlled by a user-specific psychological threshold. We then formulate a joint caching and recommendation problem maximizing the successful offloading probability, which is a mixed integer programming problem. We develop a hierarchical iterative algorithm to solve the problem when the threshold is known. Since the user threshold is unknown in practice, we proceed to propose an $\varepsilon$-greedy algorithm to find the solution by learning the threshold via interactions with users. Simulation results show that the proposed algorithms improve the successful offloading probability compared with prior works with&#x002F;without recommendation. The $\varepsilon$-greedy algorithm learns the user threshold quickly, and achieves more than $1- \varepsilon$ of the performance obtained by the algorithm with known threshold.

A Learning-Based Approach to Joint Content Caching and Recommendation at Base Stations

The gain from proactive caching at mobile devices highly relies on the accurate prediction of user demands and mobility, which, however, is hard to achieve due to the random user behavior. In this paper, we leverage personalized content recommendation to reduce the uncertainty of user demands in sending requests. We formulate a joint content pushing and recommendation problem that maximizes the net profit of a mobile network operator. To cope with the challenges in modeling and learning user behavior, we establish a reinforcement learning (RL) framework to resolve the problem. To circumvent the curse of dimensionality of reinforcement learning for the joint problem, that is, with very large action and state spaces, we decompose the original problem into two RL problems, where two agents with different goals operate together, and we limit the number of possible actions in each state of the pushing agent by harnessing the well-learned recommendation policy. To enable the generalization of action values from experienced states to the unexperienced states with function approximation, we find a proper way to represent the state and action of the pushing agent. Then, we resort to double deep-Q network with dueling architecture to solve the two problems. The simulation results show that the learned recommendation and pushing policies are able to converge and can increase the net profit significantly compared with baseline policies.

/pdf/a-deep-reinforcement-learning-approach-to-proactive-content-3ondif1kd6.pdf

A Deep Reinforcement Learning Approach to Proactive Content Pushing and Recommendation for Mobile Users

Web search engines often involve a complex pipeline of processing stages including computing, scoring, and ranking potential answers plus returning the sorted results. The latency of such pipelines can be improved by minimizing data movement, making stages faster, and merging stages. The throughput is determined by the stage with the smallest capacity and it can be improved by allocating enough parallel resources to each stage. In this paper we explore the possibility of employing hardware acceleration (an FPGA) as a way to improve the overall performance when computing answers to search queries. With a real use case as a baseline and motivation, we focus on accelerating the scoring function implemented as a decision tree ensemble, a common approach to scoring and classification in search systems. Our solution uses a novel decision tree ensemble implementation on an FPGA to: 1) increase the number of entries that can be scored per unit of time, and 2) provide a compact implementation that can be combined with previous stages. The resulting system, tested in Amazon F1 instances, significantly improves the quality of the search results and improves performance by two orders of magnitude over the existing CPU based solution.

/pdf/lowering-the-latency-of-data-processing-pipelines-through-4ny4f8w2ra.pdf

Lowering the latency of data processing pipelines through FPGA based hardware acceleration

With the exponential increase in the amount of digital information over the internet, online shops, online music, video and image libraries, search engines and recommendation system have become the most convenient ways to find relevant information within a short time. In the recent times, deep learning's advances have gained significant attention in the field of speech recognition, image processing and natural language processing. Meanwhile, several recent studies have shown the utility of deep learning in the area of recommendation systems and information retrieval as well. In this short review, we cover the recent advances made in the field of recommendation using various variants of deep learning technology. We organize the review in three parts: Collaborative system, Content based system and Hybrid system. The review also discusses the contribution of deep learning integrated recommendation systems into several application domains. The review concludes by discussion of the impact of deep learning in recommendation system in various domain and whether deep learning has shown any significant improvement over the conventional systems for recommendation. Finally, we also provide future directions of research which are possible based on the current state of use of deep learning in recommendation systems.

/pdf/use-of-deep-learning-in-modern-recommendation-system-a-1sewum8cbn.pdf

Use of Deep Learning in Modern Recommendation System: A Summary of Recent Works

/pdf/use-of-deep-learning-in-modern-recommendation-system-a-bgdca5uel4.pdf

The demand for stream processing is increasing at an unprecedented rate. Big data is no longer limited to processing of big volumes of data. In most real-world scenarios, the need for processing stream data as it comes can only meet the business needs. It is required for trading, fraud detection, system monitoring, product maintenance and of course social media data such as Twitter and YouTube videos. In such cases, a "too late architecture" that focuses on batch processing cannot realize the use cases. In this article, we present an end to end Big data platform called AlertMix for processing multi-source streaming data. Its architecture and how various Big data technologies are utilized are explained in this work. We present the performance of our platform on real live streaming data which is currently handled by the platform.

Rakesh Pant

Papers

Use of Deep Learning in Modern Recommendation System: A Summary of Recent Works

Use of Deep Learning in Modern Recommendation System: A Summary of Recent Works

AlertMix: A Big Data platform for multi-source streaming data.